AI Safety

Robust Safety Classifier Against Jailbreaking Attacks: Adversarial Prompt Shield NAACL 2024 Robust Stable Spiking Neural Networks ICML 2024 Robust Uncertainty Quantification Using Conformalised Monte Carlo Prediction AAAI 2024 R-Tuning: Instructing Large Language Models to Say ‘I Don’t Know’ NAACL 2024 Rule Based Rewards for Language Model Safety NeurIPS 2024 Run-Time Task Composition with Safety Semantics ICML 2024 Safe and Robust Subgame Exploitation in Imperfect Information Games ICML 2024 SafeAR: Safe Algorithmic Recourse by Risk-Aware Policies AAAI 2024 Safe Bayesian Optimization for the Control of High-Dimensional Embodied Systems CoRL 2024 SafeDecoding: Defending against Jailbreak Attacks via Safety-Aware Decoding ACL 2024 Safe-Embed: Unveiling the Safety-Critical Knowledge of Sentence Encoders ACL 2024 Safe Exploration in Dose Finding Clinical Trials with Heterogeneous Participants ICML 2024 Safeguarded Progress in Reinforcement Learning: Safe Bayesian Exploration for Control Policy Synthesis AAAI 2024 Safe Linear Bandits over Unknown Polytopes COLT 2024 Safe LoRA: The Silver Lining of Reducing Safety Risks when Finetuning Large Language Models NeurIPS 2024 Safe Reinforcement Learning using Finite-Horizon Gradient-based Estimation ICML 2024 Safe Reinforcement Learning with Instantaneous Constraints: The Role of Aggressive Exploration AAAI 2024 Safe RLHF: Safe Reinforcement Learning from Human Feedback ICLR 2024 SafeSora: Towards Safety Alignment of Text2Video Generation via a Human Preference Dataset NeurIPS 2024 Safety Alignment in NLP Tasks: Weakly Aligned Summarization as an In-Context Attack ACL 2024 Safety Arithmetic: A Framework for Test-time Safety Alignment of Language Models by Steering Parameters and Activations EMNLP 2024 SafetyBench: Evaluating the Safety of Large Language Models ACL 2024 Safety filters for black-box dynamical systems by learning discriminating hyperplanes L4DC 2024 Safety Fine-Tuning at (Almost) No Cost: A Baseline for Vision Large Language Models ICML 2024 SAFETY-J: Evaluating Safety with Critique EMNLP 2024